UMat& UMat::setTo(InputArray _value, InputArray _mask)
{
bool haveMask = !_mask.empty();
#ifdef HAVE_OPENCL
int tp = type(), cn = CV_MAT_CN(tp), d = CV_MAT_DEPTH(tp);
if( dims <= 2 && cn <= 4 && CV_MAT_DEPTH(tp) < CV_64F && ocl::useOpenCL() )
{
Mat value = _value.getMat();
CV_Assert( checkScalar(value, type(), _value.kind(), _InputArray::UMAT) );
int kercn = haveMask || cn == 3 ? cn : std::max(cn, ocl::predictOptimalVectorWidth(*this)),
kertp = CV_MAKE_TYPE(d, kercn);
double buf[16] = { 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0 };
convertAndUnrollScalar(value, tp, (uchar *)buf, kercn / cn);
int scalarcn = kercn == 3 ? 4 : kercn, rowsPerWI = ocl::Device::getDefault().isIntel() ? 4 : 1;
String opts = format("-D dstT=%s -D rowsPerWI=%d -D dstST=%s -D dstT1=%s -D cn=%d",
ocl::memopTypeToStr(kertp), rowsPerWI,
ocl::memopTypeToStr(CV_MAKETYPE(d, scalarcn)),
ocl::memopTypeToStr(d), kercn);
ocl::Kernel setK(haveMask ? "setMask" : "set", ocl::core::copyset_oclsrc, opts);
if( !setK.empty() )
{
ocl::KernelArg scalararg(0, 0, 0, 0, buf, CV_ELEM_SIZE(d) * scalarcn);
UMat mask;
if( haveMask )
{
mask = _mask.getUMat();
CV_Assert( mask.size() == size() && mask.type() == CV_8UC1 );
ocl::KernelArg maskarg = ocl::KernelArg::ReadOnlyNoSize(mask),
dstarg = ocl::KernelArg::ReadWrite(*this);
setK.args(maskarg, dstarg, scalararg);
}
else
{
ocl::KernelArg dstarg = ocl::KernelArg::WriteOnly(*this, cn, kercn);
setK.args(dstarg, scalararg);
}
size_t globalsize[] = { cols * cn / kercn, (rows + rowsPerWI - 1) / rowsPerWI };
if( setK.run(2, globalsize, NULL, false) )
{
CV_IMPL_ADD(CV_IMPL_OCL);
return *this;
}
}
}
#endif
Mat m = getMat(haveMask ? ACCESS_RW : ACCESS_WRITE);
m.setTo(_value, _mask);
return *this;
}
UMat& UMat::setTo(InputArray _value, InputArray _mask)
{
bool haveMask = !_mask.empty();
int tp = type(), cn = CV_MAT_CN(tp);
if( dims <= 2 && cn <= 4 && cn != 3 && ocl::useOpenCL() )
{
Mat value = _value.getMat();
CV_Assert( checkScalar(value, type(), _value.kind(), _InputArray::UMAT) );
double buf[4];
convertAndUnrollScalar(value, tp, (uchar*)buf, 1);
char opts[1024];
sprintf(opts, "-D dstT=%s", ocl::memopTypeToStr(tp));
ocl::Kernel setK(haveMask ? "setMask" : "set", ocl::core::copyset_oclsrc, opts);
if( !setK.empty() )
{
ocl::KernelArg scalararg(0, 0, 0, buf, CV_ELEM_SIZE(tp));
UMat mask;
if( haveMask )
{
mask = _mask.getUMat();
CV_Assert( mask.size() == size() && mask.type() == CV_8U );
ocl::KernelArg maskarg = ocl::KernelArg::ReadOnlyNoSize(mask);
ocl::KernelArg dstarg = ocl::KernelArg::ReadWrite(*this);
setK.args(maskarg, dstarg, scalararg);
}
else
{
ocl::KernelArg dstarg = ocl::KernelArg::WriteOnly(*this);
setK.args(dstarg, scalararg);
}
size_t globalsize[] = { cols, rows };
if( setK.run(2, globalsize, 0, false) )
return *this;
}
}
Mat m = getMat(haveMask ? ACCESS_RW : ACCESS_WRITE);
m.setTo(_value, _mask);
return *this;
}
Mat& Mat::setTo(InputArray _value, InputArray _mask)
{
if( !data )
return *this;
Mat value = _value.getMat(), mask = _mask.getMat();
CV_Assert( checkScalar(value, type(), _value.kind(), _InputArray::MAT ));
CV_Assert( mask.empty() || mask.type() == CV_8U );
size_t esz = elemSize();
BinaryFunc copymask = getCopyMaskFunc(esz);
const Mat* arrays[] = { this, !mask.empty() ? &mask : 0, 0 };
uchar* ptrs[2]={0,0};
NAryMatIterator it(arrays, ptrs);
int total = (int)it.size, blockSize0 = std::min(total, (int)((BLOCK_SIZE + esz-1)/esz));
AutoBuffer<uchar> _scbuf(blockSize0*esz + 32);
uchar* scbuf = alignPtr((uchar*)_scbuf, (int)sizeof(double));
convertAndUnrollScalar( value, type(), scbuf, blockSize0 );
for( size_t i = 0; i < it.nplanes; i++, ++it )
{
for( int j = 0; j < total; j += blockSize0 )
{
Size sz(std::min(blockSize0, total - j), 1);
size_t blockSize = sz.width*esz;
if( ptrs[1] )
{
copymask(scbuf, 0, ptrs[1], 0, ptrs[0], 0, sz, &esz);
ptrs[1] += sz.width;
}
else
memcpy(ptrs[0], scbuf, blockSize);
ptrs[0] += blockSize;
}
}
return *this;
}
